This repository provides code for machine learning algorithms for edge devices developed at Microsoft Research India.

📕machine learning tech collections at Microsoft and subsidiaries.

Online video stabilization using a novel MeshFlow motion model

An automated Microsoft Rewards bot supporting both legacy and new dashboards. Features smart automatic dashboard detection and a clean, simple interface.

Learn to build and customize multi-agent systems using the AutoGen. The course teaches you to implement complex AI applications through agent collaboration and advanced design patterns.

Code accompanying the CVPR 2019 paper: https://arxiv.org/abs/1812.04155

SPARROW — Solar-Powered Acoustic and Remote Recording Observation Watch. An AI-enabled edge device for biodiversity monitoring with camera-trap imaging and bioacoustic recording. By Microsoft AI for Good Lab.

MegaDetector V6 — Microsoft AI for Good Lab's open-source model that detects animals, people, and vehicles in camera-trap images, filtering blanks to speed wildlife research.

Re-implementation and extension of the work described in "Learning to Represent Programs with Graphs"

Solutions to Imperial College London's Natural Number Game, a gamified formal mathematics course on the Peano axioms using an interactive + automated theorem prover developed by Microsoft Research called Lean.

PyTorch-Wildlife — The Microsoft collaborative deep learning framework for conservation. Multi-task computer vision and bioacoustic models for camera-trap detection, species classification, and biodiversity monitoring. Maintained by Microsoft AI for Good Lab.

MegaDetector-Acoustic — The Microsoft open-source AI for bioacoustic biodiversity monitoring. Audio classification and species identification from sound recordings, for terrestrial bioacoustics. Maintained by Microsoft AI for Good Lab. Part of the Pytorch-Wildlife ecosystem.

Extraction tool to parse MS Celeb dataset

High-Quality Linear Interpolation for Demosaicing of Bayer-Patterned Color Images

GraphRAG-SimpleUI-Builder: Advanced Data Search and Visualization

MSRB Marketplace

Build and operate production-grade AI agent systems through this 22-chapter technical course designed for collaborative learning with AI partners.

Microsoft Research framework for training AI agents with reinforcement learning.

AutoGen Studio — Microsoft no-code GUI for building multi-agent AutoGen workflows